Date:         Wed, 23 Jan 2008 13:17:00 -0500
Reply-To:     H <lea4d@YAHOO.COM>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         H <lea4d@YAHOO.COM>
Subject:      Re: matching cases-controls

Thank you!

You are so very right by asking whether this is necessary, or useful? I
have already discussed this issue several times with my supervisors they
insist that i should match, whereas my statistician does not agree.

In the end what i look is the odds ratio between the patients and
controls.the rest of the analyses ( e.g. clustering of the variables, 683
variables i have; for that i will not use the matchied pairs)

So i will only use the matched pairs to see the odds between these cases
and controls.

Many thanks
H

=====================
To manage your subscription to SPSSX-L, send a message to
LISTSERV@LISTSERV.UGA.EDU (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD